
Scan prompts, tool definitions and model output for injection, and guard tool calls
Runs locally- Open source
- AI models and LLM tooling

Scan prompts, tool definitions and model output for injection, and guard tool calls
Runs locallyLets AI agents fetch TOTP codes for the shared 2FA accounts your team keeps in Authn8
Not checked yetPassive-by-default OSINT lookups for AI agents: DNS, WHOIS, IP, breaches, Shodan and more
Runs locally
Back up and restore Discord servers, verify members and manage them through chat
Not checked yet
IP geolocation, ASN, VPN and proxy detection and time-zone lookups for AI clients
Runs locallyFact-check LLM output claim by claim and gate risky agent actions with a safety layer
Not checked yetLocal security scanner that checks AI-written code and drives a scan, fix, rescan loop
Runs locallyLook up Windows and Entra error codes, explain logs and check IPs against blocklists
Not checked yetReview and block risky AI agent actions, installs and MCP calls on your machine
Runs locallyPersistent sandbox for coding agents: run commands, edit files, manage Git and sessions
Not checked yetCheck a Packagist package version for known vulnerabilities and release facts
Not checked yetGives agents a persistent email address, encrypted vault, audit trail and trust score
Not checked yetOpen-source MCP gate that signs an allow, deny or hold before each agent tool call
Not checked yetGenerate governance packs, approval gates and audit evidence for agents before launch
Not checked yetScreen x402 agent payments before signing: allow, hold or block with a signed receipt
Not checked yetRead-only CVE triage that explains each verdict from KEV, EPSS and exploit data
Runs locallyTelegram MCP server with a separate key per AI client, scoped to chosen chats
Runs locallyRead-only Solana token risk scores from 0 to 100 with plain-English reasons
Not checked yetCryptographic identity, delegation and receipts for AI agents, with 154 MCP tools
Not checked yetCheck artifacts and action receipts from AI agents for empty content and tampering
Not checked yetSigned receipts and reserve, spend and reconciliation checks for agents that move money
Not checked yetBlocks destructive SQL before it reaches your PostgreSQL or MySQL database
Runs locallySigned, sealed handoffs between AI agents, with trust decided by the receiver
Runs locallyScan npm packages, agent skills and MCP servers for malware before installing them
Not checked yetRead-only WordPress diagnosis from your AI, with evidence for security and speed
Not checked yetGive an AI agent its own DID: prove identity offline, verify bundles, pay and message
Not checked yetMCP server and CLI giving coding agents version-matched docs and a dependency check
Runs locallyChecks an x402 endpoint before an agent pays: pay, skip or recheck, with a signed receipt
Not checked yetEnd-to-end encrypted, read-once messaging between AI agents, with a free tier
Not checked yetRun 124 security checks on AI agents and MCP configs from your coding assistant
Runs locallySee every kind of AI for security: tools, agents, MCP servers and skills.Ranked: the best AI for security.